Epoch: 0001 train_loss= 0.69971 train_acc= 0.46364 val_loss= 0.69948 val_acc= 0.42623 time= 0.20357
Epoch: 0002 train_loss= 0.69891 train_acc= 0.46970 val_loss= 0.69841 val_acc= 0.42623 time= 0.01563
Epoch: 0003 train_loss= 0.69821 train_acc= 0.50909 val_loss= 0.69746 val_acc= 0.57377 time= 0.00000
Epoch: 0004 train_loss= 0.69771 train_acc= 0.51818 val_loss= 0.69661 val_acc= 0.57377 time= 0.00000
Epoch: 0005 train_loss= 0.69727 train_acc= 0.51818 val_loss= 0.69584 val_acc= 0.57377 time= 0.01563
Epoch: 0006 train_loss= 0.69672 train_acc= 0.53636 val_loss= 0.69516 val_acc= 0.57377 time= 0.01563
Epoch: 0007 train_loss= 0.69621 train_acc= 0.53030 val_loss= 0.69449 val_acc= 0.57377 time= 0.00000
Epoch: 0008 train_loss= 0.69572 train_acc= 0.53939 val_loss= 0.69380 val_acc= 0.57377 time= 0.01563
Epoch: 0009 train_loss= 0.69560 train_acc= 0.53939 val_loss= 0.69315 val_acc= 0.57377 time= 0.00000
Epoch: 0010 train_loss= 0.69484 train_acc= 0.53939 val_loss= 0.69243 val_acc= 0.57377 time= 0.01563
Epoch: 0011 train_loss= 0.69476 train_acc= 0.53939 val_loss= 0.69162 val_acc= 0.57377 time= 0.01563
Epoch: 0012 train_loss= 0.69430 train_acc= 0.53939 val_loss= 0.69077 val_acc= 0.57377 time= 0.00000
Epoch: 0013 train_loss= 0.69372 train_acc= 0.53939 val_loss= 0.68977 val_acc= 0.57377 time= 0.01563
Epoch: 0014 train_loss= 0.69378 train_acc= 0.53939 val_loss= 0.68892 val_acc= 0.57377 time= 0.01563
Epoch: 0015 train_loss= 0.69321 train_acc= 0.53939 val_loss= 0.68813 val_acc= 0.57377 time= 0.01060
Epoch: 0016 train_loss= 0.69376 train_acc= 0.53939 val_loss= 0.68750 val_acc= 0.57377 time= 0.00705
Epoch: 0017 train_loss= 0.69390 train_acc= 0.53939 val_loss= 0.68706 val_acc= 0.57377 time= 0.00000
Epoch: 0018 train_loss= 0.69308 train_acc= 0.53939 val_loss= 0.68680 val_acc= 0.57377 time= 0.01563
Epoch: 0019 train_loss= 0.69320 train_acc= 0.53939 val_loss= 0.68666 val_acc= 0.57377 time= 0.01563
Epoch: 0020 train_loss= 0.69336 train_acc= 0.53939 val_loss= 0.68662 val_acc= 0.57377 time= 0.00000
Epoch: 0021 train_loss= 0.69259 train_acc= 0.53939 val_loss= 0.68662 val_acc= 0.57377 time= 0.01563
Epoch: 0022 train_loss= 0.69314 train_acc= 0.53939 val_loss= 0.68673 val_acc= 0.57377 time= 0.01563
Epoch: 0023 train_loss= 0.69318 train_acc= 0.53939 val_loss= 0.68696 val_acc= 0.57377 time= 0.00000
Epoch: 0024 train_loss= 0.69296 train_acc= 0.53939 val_loss= 0.68720 val_acc= 0.57377 time= 0.01563
Epoch: 0025 train_loss= 0.69200 train_acc= 0.53939 val_loss= 0.68736 val_acc= 0.57377 time= 0.01563
Early stopping...
Optimization Finished!
Test set results: cost= 0.69766 accuracy= 0.46721 time= 0.00000 
